Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to action and events happening in a political context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    isks
    -0.72
    Characters
    -0.63
    hig
    -0.61
    GG
    -0.61
    itiveness
    -0.61
    ensity
    -0.60
    Products
    -0.60
    teness
    -0.59
     GOODMAN
    -0.59
    ÙIJ
    -0.59
    POSITIVE LOGITS
     himself
    1.20
     assassinated
    0.95
     fame
    0.93
     unsuccessfully
    0.87
     famously
    0.83
     wife
    0.83
     Himself
    0.82
     stint
    0.81
     controvers
    0.78
     tragically
    0.77
    Act Density 1.373%

    No Known Activations